Context-Aware Question Answering on TriState-Bench Scor
92.5Exact Match (EM)Greedy
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GreedyModel=Llama3-8B-Inst2026.06 | 92.5 | 95.96 | |
| AdaCADModel=Llama3-8B-Inst2026.06 | 91.75 | 95.13 | |
| GreedyBackbone=Mistral-7B2026.06 | 91.25 | 94.75 | |
| AdaCADBackbone=Mistral-7B2026.06 | 91 | 94.25 | |
| CADBackbone=Mistral-7B, alpha=0.252026.06 | 90.75 | 94.14 | |
| COIECDModel=Llama3-8B-Inst2026.06 | 90.25 | 93.75 | |
| GreedyModel=Qwen2.5-7B2026.06 | 89.5 | 93.32 | |
| ARRBackbone=Mistral-7B2026.06 | 88 | 92.73 | |
| CoCoAModel=Llama3-8B-Inst2026.06 | 87.25 | 92.06 | |
| CADBackbone=Mistral-7B, alpha=0.52026.06 | 87 | 91.08 | |
| ARRModel=Llama3-8B-Inst2026.06 | 86.75 | 91.75 | |
| GreedyModel=Llama2-13B2026.06 | 86.5 | 90.79 | |
| ARRModel=Qwen2.5-7B2026.06 | 85.75 | 91.09 | |
| CADModel=Llama2-13B, alpha=0.252026.06 | 85.25 | 89.85 | |
| AdaCADModel=Llama2-13B2026.06 | 85.25 | 89.83 | |
| COIECDBackbone=Mistral-7B2026.06 | 85 | 89.46 | |
| AdaCADModel=Mistral-7B-Inst2026.06 | 84.75 | 89.98 | |
| ARRModel=Llama2-13B2026.06 | 84 | 89.12 | |
| AdaCADModel=Qwen2.5-7B2026.06 | 81.25 | 87.5 | |
| GreedyModel=Mistral-7B-Inst2026.06 | 81 | 87.37 | |
| COIECDModel=Mistral-7B-Inst2026.06 | 80.75 | 87.33 | |
| CADModel=Llama2-13B, alpha=0.52026.06 | 80.25 | 85.44 | |
| CoCoAModel=Llama2-13B2026.06 | 80.25 | 85.44 | |
| COIECDModel=Llama2-13B2026.06 | 80 | 84.91 | |
| CADBackbone=Mistral-7B, alpha=0.752026.06 | 79.75 | 85.47 | |
| AdaCADModel=Llama2-13B-Inst2026.06 | 78.5 | 86.7 | |
| CADModel=Qwen2.5-7B, alpha=0.252026.06 | 77.5 | 84.72 | |
| GreedyModel=Llama2-13B-Inst2026.06 | 77 | 85.3 | |
| ARRModel=Mistral-7B-Inst2026.06 | 76.5 | 83.66 | |
| CADModel=Mistral-7B-Inst2026.06 | 75.25 | 83.26 | |
| ARRBackbone=Llama3-8B2026.06 | 75 | 82.68 | |
| COIECDModel=Llama2-13B-Inst2026.06 | 74.2 | 83.7 | |
| CADModel=Llama2-13B, alpha=0.752026.06 | 73.5 | 80.52 | |
| Simple InterpModel=Qwen2.5-7B, tau=0.752026.06 | 73 | 80.68 | |
| Simple InterpModel=Llama2-13B, tau=0.752026.06 | 71.5 | 75.91 | |
| Simple InterpBackbone=Llama3-8B, tau=0.752026.06 | 70.5 | 79.25 | |
| CADBackbone=Mistral-7B, alpha=1.02026.06 | 70.5 | 78.48 | |
| CADModel=Llama2-13B, alpha=1.02026.06 | 66 | 75.74 | |
| Simple InterpBackbone=Mistral-7B, tau=0.752026.06 | 66 | 74.97 | |
| COIECDModel=Qwen2.5-7B2026.06 | 65.75 | 76.63 | |
| CADModel=Llama3-8B-Inst2026.06 | 60.75 | 75.38 | |
| GreedyBackbone=Llama3-8B2026.06 | 59.5 | 70.79 | |
| ARRModel=Llama2-13B-Inst2026.06 | 59.2 | 72.8 | |
| CADModel=Qwen2.5-7B, alpha=0.52026.06 | 58.5 | 71.46 | |
| CoCoABackbone=Mistral-7B2026.06 | 55.5 | 70.1 | |
| AdaCADBackbone=Llama3-8B2026.06 | 51.5 | 64.19 | |
| CADModel=Llama2-13B-Inst2026.06 | 50.2 | 68.8 | |
| CADBackbone=Llama3-8B, alpha=0.252026.06 | 44.5 | 58 | |
| Simple InterpBackbone=Llama3-8B, tau=0.52026.06 | 40.75 | 52.66 | |
| CADModel=Qwen2.5-7B, alpha=0.752026.06 | 38.5 | 57.62 | |
| Simple InterpModel=Llama2-13B, tau=0.52026.06 | 38.5 | 43.86 | |
| CADBackbone=Llama3-8B, alpha=0.52026.06 | 33 | 49.35 | |
| Simple InterpModel=Qwen2.5-7B, tau=0.52026.06 | 31.25 | 48.41 | |
| CoCoABackbone=Llama3-8B2026.06 | 31.25 | 47.88 | |
| COIECDBackbone=Llama3-8B2026.06 | 30.25 | 47.35 | |
| CADBackbone=Llama3-8B, alpha=0.752026.06 | 26.75 | 44.72 | |
| CoCoAModel=Qwen2.5-7B2026.06 | 26.5 | 46.41 | |
| CADModel=Qwen2.5-7B, alpha=1.02026.06 | 25.75 | 49.65 | |
| CADBackbone=Llama3-8B, alpha=1.02026.06 | 21.75 | 41.07 | |
| Simple InterpBackbone=Mistral-7B, tau=0.52026.06 | 20.5 | 34.15 | |
| Simple InterpModel=Llama2-13B, tau=0.252026.06 | 11.75 | 18.25 | |
| CoCoAModel=Llama2-13B-Inst2026.06 | 11.5 | 59.8 | |
| Simple InterpBackbone=Llama3-8B, tau=0.252026.06 | 10.5 | 20.31 | |
| CADModel=Qwen2.5-7B-Inst2026.06 | 6.5 | 27.93 | |
| Simple InterpModel=Qwen2.5-7B, tau=0.252026.06 | 6 | 20.6 | |
| COIECDModel=Qwen2.5-7B-Inst2026.06 | 2.5 | 25.23 | |
| AdaCADModel=Qwen2.5-7B-Inst2026.06 | 2.5 | 27.64 | |
| CoCoAModel=Qwen2.5-7B-Inst2026.06 | 2.5 | 27.15 | |
| Simple InterpBackbone=Mistral-7B, tau=0.252026.06 | 2.25 | 14.2 | |
| Greedy_no_ctxBackbone=Llama3-8B2026.06 | 2 | 11.33 | |
| GreedyModel=Qwen2.5-7B-Inst2026.06 | 1.25 | 27.81 | |
| ARRModel=Qwen2.5-7B-Inst2026.06 | 0.75 | 24.44 | |
| CoCoAModel=Mistral-7B-Inst2026.06 | 0.5 | 28.03 | |
| Greedy_no_ctxModel=Qwen2.5-7B2026.06 | 0 | 8.76 | |
| Greedy_no_ctxModel=Llama2-13B2026.06 | 0 | 8.16 | |
| Greedy_no_ctxBackbone=Mistral-7B2026.06 | 0 | 8.96 |